{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FRQASMNILNRZUZ7M6WJM2O3TI4","short_pith_number":"pith:FRQASMNI","canonical_record":{"source":{"id":"2501.01956","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T18:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"fbf1efc001df94cf10fcb20dc14b4392e4ea9d47ca1a4ebc7957fa8382b39559","abstract_canon_sha256":"e8c532f87e00d12bb20a9125642649ac87cb111f131478f1b48941393a4ddf00"},"schema_version":"1.0"},"canonical_sha256":"2c600931a85b639a67ecf592cd3b73472f8205bff215b90de9c6f96c64731f81","source":{"kind":"arxiv","id":"2501.01956","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01956","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01956v3","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01956","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"FRQASMNILNRZ","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"FRQASMNILNRZUZ7M","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"FRQASMNI","created_at":"2026-07-05T11:28:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FRQASMNILNRZUZ7M6WJM2O3TI4","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01956","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T18:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"fbf1efc001df94cf10fcb20dc14b4392e4ea9d47ca1a4ebc7957fa8382b39559","abstract_canon_sha256":"e8c532f87e00d12bb20a9125642649ac87cb111f131478f1b48941393a4ddf00"},"schema_version":"1.0"},"canonical_sha256":"2c600931a85b639a67ecf592cd3b73472f8205bff215b90de9c6f96c64731f81","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:13.379297Z","signature_b64":"ANtf0vy0869dfg8FO77rLLZT7itq6V0Ddd3Q2Swtb1cRnFLs8G6+H9A7KLsp0rsDgsHzQt4BtrXKzMlas4VHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c600931a85b639a67ecf592cd3b73472f8205bff215b90de9c6f96c64731f81","last_reissued_at":"2026-07-05T11:28:13.378802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:13.378802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01956","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEXriRr/eVGjoFRpPHK2pVwzaeAtma2K5l7OZQuiY3UETNvnR0JwQy0X+bJxF7Y6KXGQ1NG0dLANf6DMPBVNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:28:03.951710Z"},"content_sha256":"9f15db58ba719d5fbd8db1af2c793dd72f5b5248d7ac84b546f278c7d7ac16e1","schema_version":"1.0","event_id":"sha256:9f15db58ba719d5fbd8db1af2c793dd72f5b5248d7ac84b546f278c7d7ac16e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FRQASMNILNRZUZ7M6WJM2O3TI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Metadata Conditioning Accelerates Language Model Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Wettig, Danqi Chen, Luxi He, Sadhika Malladi, Tianyu Gao, Yihe Dong","submitted_at":"2025-01-03T18:59:23Z","abstract_excerpt":"The vast diversity of styles, domains, and quality levels present in language model pre-training corpora is essential in developing general model capabilities, but efficiently learning and deploying the correct behaviors exemplified in each of these heterogeneous data sources is challenging. To address this, we propose a new method, termed Metadata Conditioning then Cooldown (MeCo), to incorporate additional learning cues during pre-training. MeCo first provides metadata (e.g., URLs like www$.$wikipedia$.$org) alongside the text during training and later uses a cooldown phase with only the sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01956","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.01956/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8UPkxXuez45MNWynLfHp9Za+BoBfSBcD088+0jpYZ2dIm2Rw4wYU3P+Th4+dRb+H3x/GAW69DSOyAR9yoXSOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T02:28:03.952109Z"},"content_sha256":"6bee1db8682c49d36ce378f6789b122aa6444b8d8f4da73fcfa2aa0faa2bb3ac","schema_version":"1.0","event_id":"sha256:6bee1db8682c49d36ce378f6789b122aa6444b8d8f4da73fcfa2aa0faa2bb3ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRQASMNILNRZUZ7M6WJM2O3TI4/bundle.json","state_url":"https://pith.science/pith/FRQASMNILNRZUZ7M6WJM2O3TI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRQASMNILNRZUZ7M6WJM2O3TI4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T02:28:03Z","links":{"resolver":"https://pith.science/pith/FRQASMNILNRZUZ7M6WJM2O3TI4","bundle":"https://pith.science/pith/FRQASMNILNRZUZ7M6WJM2O3TI4/bundle.json","state":"https://pith.science/pith/FRQASMNILNRZUZ7M6WJM2O3TI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRQASMNILNRZUZ7M6WJM2O3TI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FRQASMNILNRZUZ7M6WJM2O3TI4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e8c532f87e00d12bb20a9125642649ac87cb111f131478f1b48941393a4ddf00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T18:59:23Z","title_canon_sha256":"fbf1efc001df94cf10fcb20dc14b4392e4ea9d47ca1a4ebc7957fa8382b39559"},"schema_version":"1.0","source":{"id":"2501.01956","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01956","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01956v3","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01956","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"FRQASMNILNRZ","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"FRQASMNILNRZUZ7M","created_at":"2026-07-05T11:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"FRQASMNI","created_at":"2026-07-05T11:28:13Z"}],"graph_snapshots":[{"event_id":"sha256:6bee1db8682c49d36ce378f6789b122aa6444b8d8f4da73fcfa2aa0faa2bb3ac","target":"graph","created_at":"2026-07-05T11:28:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.01956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vast diversity of styles, domains, and quality levels present in language model pre-training corpora is essential in developing general model capabilities, but efficiently learning and deploying the correct behaviors exemplified in each of these heterogeneous data sources is challenging. To address this, we propose a new method, termed Metadata Conditioning then Cooldown (MeCo), to incorporate additional learning cues during pre-training. MeCo first provides metadata (e.g., URLs like www$.$wikipedia$.$org) alongside the text during training and later uses a cooldown phase with only the sta","authors_text":"Alexander Wettig, Danqi Chen, Luxi He, Sadhika Malladi, Tianyu Gao, Yihe Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T18:59:23Z","title":"Metadata Conditioning Accelerates Language Model Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01956","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9f15db58ba719d5fbd8db1af2c793dd72f5b5248d7ac84b546f278c7d7ac16e1","target":"record","created_at":"2026-07-05T11:28:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e8c532f87e00d12bb20a9125642649ac87cb111f131478f1b48941393a4ddf00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-03T18:59:23Z","title_canon_sha256":"fbf1efc001df94cf10fcb20dc14b4392e4ea9d47ca1a4ebc7957fa8382b39559"},"schema_version":"1.0","source":{"id":"2501.01956","kind":"arxiv","version":3}},"canonical_sha256":"2c600931a85b639a67ecf592cd3b73472f8205bff215b90de9c6f96c64731f81","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c600931a85b639a67ecf592cd3b73472f8205bff215b90de9c6f96c64731f81","first_computed_at":"2026-07-05T11:28:13.378802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:13.378802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ANtf0vy0869dfg8FO77rLLZT7itq6V0Ddd3Q2Swtb1cRnFLs8G6+H9A7KLsp0rsDgsHzQt4BtrXKzMlas4VHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:13.379297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01956","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f15db58ba719d5fbd8db1af2c793dd72f5b5248d7ac84b546f278c7d7ac16e1","sha256:6bee1db8682c49d36ce378f6789b122aa6444b8d8f4da73fcfa2aa0faa2bb3ac"],"state_sha256":"8f5239b608efd6d155b8d8d782a40ab19e7b6a9c9e3c59ff8c44c8e5c1d872cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXE2DIwYj/oLlKf68hjw7dxFVYSDOMgPlBZaTmO2muo6irlPBcb8FCmPxxyr/F2any+atXomWzAseu61CwP5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T02:28:03.955024Z","bundle_sha256":"335ab57faff17eed77c7425f0b126b2b27460babaa7263976564b6f6db2f1991"}}